EP0689321A1 - System zur hohen Verfügbarkeit von netzwerkweiter Bandbreitenzuordnung - Google Patents

System zur hohen Verfügbarkeit von netzwerkweiter Bandbreitenzuordnung Download PDF

Info

Publication number
EP0689321A1
EP0689321A1 EP94109763A EP94109763A EP0689321A1 EP 0689321 A1 EP0689321 A1 EP 0689321A1 EP 94109763 A EP94109763 A EP 94109763A EP 94109763 A EP94109763 A EP 94109763A EP 0689321 A1 EP0689321 A1 EP 0689321A1
Authority
EP
European Patent Office
Prior art keywords
sba
allocator
bandwidth
synchronous
qos
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
EP94109763A
Other languages
English (en)
French (fr)
Inventor
Jeff Warren
Pascal Francois
Frederic Raimbault
Eric Lebrun
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
International Business Machines Corp
Original Assignee
International Business Machines Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by International Business Machines Corp filed Critical International Business Machines Corp
Priority to EP94109763A priority Critical patent/EP0689321A1/de
Priority to US08/493,066 priority patent/US5548579A/en
Publication of EP0689321A1 publication Critical patent/EP0689321A1/de
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/70Admission control; Resource allocation
    • H04L47/78Architectures of resource allocation
    • H04L47/781Centralised allocation of resources
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00Data switching networks
    • H04L12/28Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
    • H04L12/42Loop networks
    • H04L12/427Loop networks with decentralised control
    • H04L12/433Loop networks with decentralised control with asynchronous transmission, e.g. token ring, register insertion
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00Data switching networks
    • H04L12/64Hybrid switching systems
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/70Admission control; Resource allocation
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/70Admission control; Resource allocation
    • H04L47/74Admission control; Resource allocation measures in reaction to resource unavailability
    • H04L47/746Reaction triggered by a failure

Definitions

  • the present invention relates to the data communication field and more particularly to a system for high availability of network-wide bandwidth allocation over a network made of at least one FDDI segment.
  • QoS Quality of Service
  • Fiber Distributed Data Interface (FDDI) standard describes a dual counter-rotating fiber-optic ring operating at 100 MBps.
  • FDDI Fiber Distributed Data Interface
  • One of the prime interests in FDDI is the establishment of a network made of a very high-speed backbone (the FDDI segment) interconnecting heterogeneous Local Area Networks (LANs).
  • LANs Local Area Networks
  • Network-wide bandwidth allocation over such an interconnected LAN domain is dealt with in European patent application 93480041.8 filed on April 19, 1993, by International Business Machines Corp, the teaching of which is incorporated hereafter by reference.
  • the Allocator is the component responsible for maintaining awareness of the capacity of the LAN components (i.e. bridges and segments), determining whether a particular request for a bandwidth allocation can be granted.
  • the Requestor is the component responsible for making a request to reserve a certain QoS for an application.
  • SBA Synchronous Bandwidth Allocator
  • the SBA is responsible for allocating synchronous bandwidth to applications requiring guaranteed bandwidth and predictable delay.
  • the latter piece of prior art proposes the implementation of slave SBA applications to monitor the FDDI segment and take on the role of a master SBA when needed, such process being known as High Availability SBA.
  • the 3PR receives from the QoS Allocator all information that it needs to ask for bandwidth reservation on the FDDI segment.
  • the 3PR is able to act on behalf of the FDDI station that will submit synchronous traffic and ask for bandwidth allocation to the SBA. According to the SBA decision, the 3PR will then answer to the QoS Allocator which will grant or deny the allocation over the whole path.
  • the present invention solves the problem raised by the failure of the 3PR on a Fiber Distributed Data Interface segment.
  • the concept of a master and slave entity is used to develop the high availability of 3PR model.
  • the master application is responsible for interfacing the Qos Allocator and the SBA as described in the background art.
  • the new state machine shall bring the 3PR either to an ACTIVE state where it will act as a master or to a new 3PR state called BACKUP state where it should be ready to replace the master application if it fails, or even to a STANDBY state where it stops since there are already master and backup applications.
  • the decision to go to ACTIVE , BACKUP or STANDBY state is directly dependent on the state of the SBA in the same station as of the 3PR application According to the state of the SBA present in that station, the 3PR shall into the same state. It is mandatory to have these 2 applications on the same station: it prevents from increasing traffic over the FDDI segment and is more efficient since allocations requests /responses are going to the same station.
  • the SBA High Availability process forces the acting SBA to move to another station, the 3PR shall follow as well and start on this new station.
  • the newly inserting 3PR application learns if SBA application is master by transmitting an Request Allocation frame (RAF) request with an NULL payload. Since these 2 applications shall reside on the same station, the Source Address of the RAF response sent by the master SBA shall determine if it runs on the master SBA station. If this address doesn't match its own , then the newly inserting 3PR application should get the address of the slave SBA (vendor specific MIB attribute kept in the master SBA MIB).
  • RAF Request Allocation frame
  • the 3PR detects that it runs over the slave SBA station , it shall go into the BACKUP state . If none of these addresses match its own , it shall go into the standby state.
  • the slave 3PR shall monitor the SBA_Hello request and SBA_Hello responses. If a SBA_Response is missing, the slave 3PR shall get a MIB attribute (SBA Available) which will indicate if the slave SBA became a master SBA. In this case, the slave 3PR becomes the master 3PR.
  • MIB attribute SBA Available
  • the effect of the invention is thus to allow a redundant 3PR application to detect a failure from a SBA or from the master 3PR and then provide High Availability Service between the QoS Allocator and the High Availability SBA.
  • the invention comprises a system for high availability of network-wide bandwidth allocation in a network including a FDDI segment, comprising:
  • the invention comprises a system for high availability bandwidth allocation in a domain of LANs interconnected by at least one FDDI segment, comprising:
  • the second means in said third device include:
  • the allocation of Synchronous Bandwidth over an Fiber Distributed Data Interface network is performed by using the Resource Allocation frame protocol.
  • This protocol assumes one central allocator of the Synchronous Bandwidth resource, and provides for the management of Synchronous Bandwidth Allocator, the detection of over allocation, and ability to recover from faults due to over-allocation.
  • Fig.1 shows an example of an allocation of Synchronous Bandwidth.
  • a station must receive an allocation of Synchronous Bandwidth before initiating synchronous transmission.
  • a station that wants to change its current allocation of Synchronous Bandwidth must request the new allocation amount from the Synchronous Bandwidth Allocator Management station.
  • a station sends an Resource Allocation frame Request (Request Allocation) to a Synchronous Bandwidth Allocator Management station.
  • a Synchronous Bandwidth Allocator Management station will respond with an Resource Allocation frame Response indicating success or failure of the request. If the request fails, the station may adjust its allocation request to within the available bandwidth specified in the response frame and restart the exchange.
  • the Station changes its Synchronous Bandwidth attributes - ie in the Management Information Base - when response indicates successful allocation.
  • the SBA application is responsible for allocating synchronous bandwidth to applications requiring guaranteed bandwidth and predictable delay.
  • a single SBA manages an FDDI segment, each FDDI segment has one and only one SBA actively managing all synchronous traffic. If this SBA application fails, additional allocations would not be allowed, existing allocations could not increase or decrease their allocations.
  • the synchronous allocation request processing is straight forward, whereas the process of deallocation due to over-utilization or inconsistencies is not.
  • the SBA complexities are in various SBA Actions where deallocations are generated and in the allocation data structures where many SBA parameters are maintained.
  • the purpose of the Synchronous Bandwidth Management (SBM) function is to control synchronous allocations on a single FDDI segment. Allocations are limited to the primary FDDI ring. The amount of available synchronous bandwidth is set in the SBA_Available parameter.
  • the Synchronous Bandwidth Allocator is responsible for the regulation of the synchronous traffic on the FDDI ring.
  • the SBM provides recovery mechanisms to recover unused bandwidth, resolves T_Neg and reconfiguration changes.
  • Many of the SBM state diagram inputs are provided by the underlying FDDI sub-system supporting it.
  • Fig.17 shows an example of SBA state machine.
  • the SBA process begins with transition SB(00) where SBM enters the Standby State. In this state, the SBM waits for the assertion of SB_Start, this occurs after SBA initializes the SBA application.
  • the SBA monitors the FDDI segment from the Active State. Normally SBA is in this state unless an active allocation is being refreshed or SBA is recovering from an over-allocation condition.
  • SB(10) StopSBAManager - SB(11a) : AllocationRequest - SB(11b) : NIFMonitoring - SB(12) : PotentialRecoveryRequired - SB(13a) : ReportAllocation - SB(13b) : ProcessReportResponse - SB(14) : ProcessChangeResponse -
  • the Recovery state indicates SBM has detected a T_neg change potentially requiring a de-allocation of synchronous bandwidth. Entering this state causes SBM to re-evaluate all active allocations contained within the SBA MIB.
  • SB(21) RecoveryCompleted - SB(24) : RecoveryDeallocation -
  • the Report state is used to refresh active allocations and to perform active allocation consistency checks. The consistency checking is necessary to recover unused synchronous allocations when the end-station has been removed from the ring prior to deallocating its bandwidth.
  • the Change state is used by SBM to issue an SBA RAF Change allocation frame. Entry into this state occurs when Report Actions detect an allocation inconsistency or the Recovery Actions require a de-allocation to recover from a ring over-allocation condition or when an SBA RAF Change Allocation response has been received.
  • SB(41) CompletedDeallocation - SB(42) : PotentialAdditionalRecoveryRequired - SB(43) : ContinueReportProcess -
  • the failure of an SBA application is addressed by Highly Available Synchronous Bandwidth Allocator . Highly Available Synchronous Bandwidth Allocator provides extensions to the FDDI Synchronous Implementer's Agreement.
  • the SBA Internals section is modified to allow slave SBA applications to monitor the FDDI segment and take on the role of master SBA when needed (see Fig.18).
  • the concept of a master and slave allocator is used to develop the high availability SBA model.
  • the master SBA is the SBA responsible for granting or denying allocation requests as well as manage disturbances resulting from network changes, such as changes in token rotation delays.
  • the master SBA will communicate with the slave SBA (if present) to update the slave with current allocation information. These updates are communicated from master to slave via the unique extended service frame protocol using an IBM specific encoding. The updates occur when allocations are modified.
  • the underlying SBA state machine shall enter into a new SBA state called BACKUP State as opposed to directly going to the Active State.
  • the Active state is now for one and only one SBA application, the master SBA.
  • This new state is to learn if a master and/or slave are currently operational.
  • the newly inserting SBA application learns if other SBA applications are present by using an SBA_Hello Request/Response process.
  • the slave SBA This allows a redundant SBA application (the slave SBA) to keep a shadow copy of the master's SBA MIB.
  • the FDDI segment is without an SBA manager for three minutes if a slave SBA is present.
  • Detection of the master failure occurs when the slave fails to receive three consecutive master present announcements.
  • the slave detects a master failure it transitions to the Active State where it assumes the role of master. If the slave does not have all of the master's SBA MIB, the slave shall learn about the unknown data using the SBA report request protocol.
  • Network Resource Reservation - NRR Network Resource Reservation - NRR
  • QoS Requestor is needed for all LAN stations that want to send traffic requiring Quality of Service guarantees (e.g. multimedia traffic). Only a single QoS Allocator is required for a given bridged Local Area Network.
  • Fig.2 depicts the QoS Requestor and QoS Allocator structure on a Local Area Network.
  • the QoS Requestor includes the following functions:
  • the QoS Allocator includes the following functions:
  • the Qos Management protocol enables a QoS Requestor entity to register with a QoS Allocator entity in the network, and to interact with the QoS Allocator to manage network Qos for data streams.
  • Fig.3 shows QoS Allocation
  • Fig.4 QoS Deallocation
  • Fig.5 a change of QoS Allocation
  • Fig.6 a Refresh of bandwidth
  • Fig.7 the Registration Protocol.
  • the 3rd Party Requestor solves the problem raised by the allocation of synchronous bandwidth on a Fiber Distributed Data Interface segment when this allocation is done by a centralized allocator in an interconnected Local Area Network domain.
  • This centralized allocator (or QoS Allocator) is responsible to do the allocation on a network-wide basis, whatever the protocol used between the two points exchanging synchronous traffic. But to be able to do this, it needs to interact with agents responsible for bandwidth allocation on every Fiber Distributed Data Interface segment : the Synchronous Bandwidth Allocator. This interface is done by an agent named the 3rd Party Requestor.
  • This 3rd Party Requestor receives from the QoS Allocator all information that it needs to ask for bandwidth reservation on the Fiber Distributed Data Interface segment. Following the Station Management standard , the 3rd Party Requestor is able to act on behalf of the Fiber Distributed Data Interface station that will submit synchronous traffic and ask for bandwidth allocation to the Synchronous Bandwidth Allocator. According to the Synchronous Bandwidth Allocator decision, the 3rd Party Requestor will then answer to the QoS Allocator which will grant or deny the allocation over the whole path.
  • the 3rd Party Requestor enables the coexistence of two bandwidth allocation processes (the centralized allocation process from the QoS Allocater and the Synchronous Bandwidth Allocator for Fiber Distributed Data Interface segments).
  • the Fiber Distributed Data Interface bandwidth allocation process is defined by the Station Management standard defined by American National Standards Institute. It uses specific frames, named Resource Allocation Frames (RAF frames) defined by Station Management.
  • Fig.8 shows the environment for 3rd Party Requestor.
  • the 3rd Party Requester receives requests from the QoS Allocator , like 'AllocationRequest' or ChangeRequest'. Before answering by 'AllocationConfirm' or 'ChangeConfirm it should consult the Synchronous Bandwidth Allocator, authority on Fiber Distributed Data Interface segment.
  • the 3rd Party Requestor includes the following functions:
  • the QoS Management frame are used by the NRR Allocator to send QoS messages to the 3rd Party Requestor, and in return the 3rd Party Requestor will use the same type of frame to make the response.
  • the SMT RAF frame are used by the 3rd Party Requestor to request allocation to the SBA. and in return the SBA will use the same type of frame to make the response.
  • the SMT PMF frame are used by the 3rd Party Requestor to get and set SBA MIB attributes to the Synchronous Node (or NRR Requestor), and it return it will use the same type of frame to make the response.
  • the NRR Allocator initiates a request for QoS for a particular data stream over an FDDI segment, by sending an FDDIAllocateRequest message to the 3rd Party Requestor. After processing the request the 3rd Party Requestor returns an FDDIAllocateReply message. This is shown Fig.9.
  • the NRR Allocator initiates a request for a change in an existing QoS allocation for a FDDI data stream by sending an FDDIChangeRequest message to the 3rd Party Requestor. After processing the request the 3rd Party Requestor returns an FDDIChangeReply message. This is shown Fig. 10.
  • T_Neg Change shall be done by monitoring the MIB attribute fddiMACT_Neg, because this attribute is updated at each Token Rotation Time (TRT) negotiation.
  • SBA_Allocatable Change shall be done by checking the SBA Allocatable parameter in all RAF Request Allocation Response. This is shown Fig.9 or 10.
  • the detection of SBA_Available Change shall be done by monitoring the MIB attribute fddiPATHSbaAvailable, because this attribute is set at each SBA initialization.
  • the 3rd Party Requestor should send a FDDIStatusRequest with SBA Allocatable, SBA Available, and T_Neg parameters in order that QoS Allocator get these values before to process any requests. This is shown Fig.11.
  • Registration flows enable a NRR Allocator and 3rd Party Requestor to exchange network addressing information and for the 3rd Party Requestor to pass other information to the Allocator.
  • the NRR Allocator or the 3rd Party Requestor may initiate the flows.
  • the modified 3PR state machine to establish high availability 3PR (HA-3PR) functionally.
  • the High Availability 3PR state machine is described in Fig.16.
  • the invention modifications are easily identified in the box in dotted line.
  • the Init_Actions queue an RAF Request Allocation message for a NULL allocation. From the RAF Request Allocation response, the HA-3PR learns the address of the SBA-master if the SBA-master address (SBA_Master_Address) is equal at local address (My_Address), the HA-3PR asserts the TP_Start signal, and transits from the STANDBY state to the ACTIVE state.
  • SBA_Master_Address SBA-master address
  • My_Address local address
  • the Normal_Actions are performed upon this transition, the Normal_Actions are listed hereafter: If the SBA-master address (SBA_Master_Address) is different from the local address, the Init_Actions queue an PMF Get request for IBM attribute ibmPATHHA_Slave_Addr.
  • the HA-3PR learns the address of the SBA-slave: If the SBA-slave address (SBA_Slave_Address) is different from the local address (My_Address), the HA-3PR asserts the TP_Hold signal, and the HA 3PR is stopped.
  • the HA-3PR asserts the TP_Wait signal, and transits from the STANDBY state to the BACKUP state.
  • the Hello_3PR_Actions are performed upon this transition, the Hello_3PR_Actions are listed hereafter: Each time a hello request message is transmitted by the SBA-slave to the SBA-master, the HA-3PR receives an hello request message.
  • the HA-3PR receives an hello response message.
  • the HA-3PR In case of failure of the SBA-master (no hello response message received on time), the HA-3PR asserts the TP_Get signal, and transits from the BACKUP state to the GET state.
  • the Get_Actions are performed upon this transition, the Get_Actions are listed hereafter:
  • the Get_Actions queue an PMF Get request message for attribute fddiPATHSbaAvailable (as defined in the SMT standard) of the local SBA and monitors this attribute as following: the value of this attribute is equal to zero when the local SBA is SBA-slave, and the value of this attribute is different from zero when the local SBA (previously the SBA-slave) became the SBA-master.
  • the HA-3PR asserts the TP_Start signal, and transits from the GET state to the ACTIVE state.
  • the HA-3PR asserts the TP_Wait signal, and transits from the GET state to the BACKUP state.
  • the invention includes the following modifications to the variables, signals, flags, counters, and timers used within High Availability Third Party Requestor (HA-3PR):
  • a variable shall take on one value from a limited set of possible values. When a variable is cleared, the value of the variable becomes "none". Variables may be exported outside of Third Party Requestor.
  • TP_Input A variable from 3PR Frame Parser indicating the type of SMT information to be processed.
  • the 3PR shall queue the TP_Input variable each time it changes value and process them in the order received.
  • the TP_Input is processed from the ACTIVE State, the BACKUP state, and the GET state and has the following values.
  • a signal is used to initiate a state change within Third Party Requestor.
  • a signal causes the state change to occur and does not have to be cleared following its usage.
  • a signal is local to Third Party Requestor and may not be exported.
  • the signals used to drive the HA-3PR state diagram are generated by the supporting 3PR system.
  • TP_Start - A signal internal to HA-3PR used to transition to the ACTIVE State.
  • a flag is a variable that shall take on one of two values: set or cleared. Flags are assigned values within the HA-3PR state diagram by specifying a set or clear operation. Flags are tested within the HA-3PR state diagram by checking their status or the negation of their status. Transitions initiated by flags need only be checked upon initial entry into the state and upon change to the flag. The value of a flag may be exported outside of HA-3PR.
  • Begin_Flag - A flag internal to HA-3PR used to direct the Init_Actions to transmit an RAF Request Allocation request message with a NULL SBA Payload.
  • THR - Timer High Availability 3PR - THR is initialized at station initialization.
  • HA-3PR maintains a THR timer for one purpose, to trigger Hello request messages.
  • TSW - Timer SBA Switch - TSW is initialized at station initialization.
  • HA-3PR maintains a TSW timer to handle the switching time between SBA-Slave and SBA-Master.
  • Get_cnt - Get_cnt is initialized at station initialization. This counter controls the number of PMF Get requests that are transmitted in the GET state.
  • the HA-3PR process begins in the Standby State. In this state, the HA-3PR send an RAF Request Allocation request and waits for the reception of the RAF Request Allocation response to learn the individual address of the SBA-master (SBA_Master_Address), and the individual address of the SBA-slave (SBA_Slave_Address).
  • TP(00a) Start3PR - A transition to the STANDBY state is made when the HA-3PR is started.
  • the Begin_Flag has been set during the initialization of HA-3PR.
  • TP(00b) Stop3PR - A transition back to the STANDBY state is made when the TP_Hold signal is asserted. The HA-3PR is stopped.
  • TP(00c) ProcessRAFResponse - A transition back to the STANDBY state is made when the variable TP_Input is set to RAF_Response. The Init_Actions are performed upon this transition.
  • TP(01) Start3PRMaster - A transition to the ACTIVE state is made when the TP_Start signal is asserted. The Normal_Actions are performed on this transition.
  • TP(02) Start3PRSlave - A transition to the BACKUP state is made when the TP_Wait signal is asserted. The Hello_3PR_Actions are performed on this transition.
  • HA-3PR performs the same following actions that a standard 3PR:
  • the HA-3PR enters the BACKUP state after the TP_Wait signal is asserted. From this state the HA-3PR listen the FDDI ring and more specialy the Hello messages to detect any failure from the SBA-master.
  • TP(22a) ProcessHelloRequest - A transition back to the BACKUP state is made when the variable TP_Input is set to Hello_Request. The Hello_3PR_Actions are performed upon this transition.
  • TP(22b) ProcessHelloResponse - A transition back to the BACKUP state is made when the variable TP_Input is set to Hello_Response. The Hello_3PR_Actions are performed upon this transition.
  • TP(22c) HelloTimeOut - A transition back to the BACKUP state is made when the timer THR expires. The Hello_3PR_Actions are performed upon this transition.
  • TP(23) SendGetRequest - A transition to the GET state is made when the TP_Get signal is asserted. The Get_Actions are performed on this transition.
  • the HA-3PR monitors the value of the MIB attribute fddiPATHSbaAvailable in order to detect when the SBA-Slave is the SBA-master.
  • TP(31) Start3PRMaster - A transition to the ACTIVE state is made when the TP_Start signal is asserted. The Normal_Actions are performed on this transition.
  • TP(32) Start3PRSlave - A transition to the BACKUP state is made when the TP_Wait signal is asserted. The Hello_3PR_Actions are performed on this transition.
  • TP(33a) ProcessGetResponse - A transition back to the GET state is made when the variable TP_Input is set to Get_Response. The Get_Actions are performed upon this transition.
  • TP(33b) SwitchTimeOut - A transition back to the GET state is made when the timer TSW expired. The Get_Actions are performed upon this transition.
EP94109763A 1994-06-23 1994-06-23 System zur hohen Verfügbarkeit von netzwerkweiter Bandbreitenzuordnung Withdrawn EP0689321A1 (de)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP94109763A EP0689321A1 (de) 1994-06-23 1994-06-23 System zur hohen Verfügbarkeit von netzwerkweiter Bandbreitenzuordnung
US08/493,066 US5548579A (en) 1994-06-23 1995-06-21 System for effective allocation of network-wide bandwidth

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
EP94109763A EP0689321A1 (de) 1994-06-23 1994-06-23 System zur hohen Verfügbarkeit von netzwerkweiter Bandbreitenzuordnung

Publications (1)

Publication Number Publication Date
EP0689321A1 true EP0689321A1 (de) 1995-12-27

Family

ID=8216044

Family Applications (1)

Application Number Title Priority Date Filing Date
EP94109763A Withdrawn EP0689321A1 (de) 1994-06-23 1994-06-23 System zur hohen Verfügbarkeit von netzwerkweiter Bandbreitenzuordnung

Country Status (2)

Country Link
US (1) US5548579A (de)
EP (1) EP0689321A1 (de)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2381996A (en) * 2001-10-30 2003-05-14 Hewlett Packard Co Network bandwidth optimization method and system

Families Citing this family (31)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7362775B1 (en) 1996-07-02 2008-04-22 Wistaria Trading, Inc. Exchange mechanisms for digital information packages with bandwidth securitization, multichannel digital watermarks, and key management
US5613004A (en) 1995-06-07 1997-03-18 The Dice Company Steganographic method and device
EP0781068A1 (de) * 1995-12-20 1997-06-25 International Business Machines Corporation Methode und System für adaptive Bandbreitenzuordnung in einem schnellen Datennetzwerk
US7664263B2 (en) 1998-03-24 2010-02-16 Moskowitz Scott A Method for combining transfer functions with predetermined key creation
US6205249B1 (en) 1998-04-02 2001-03-20 Scott A. Moskowitz Multiple transform utilization and applications for secure digital watermarking
GB2318030B (en) * 1996-10-04 2001-03-14 Ibm Communication system with exchange of capability information
US6400681B1 (en) 1996-06-20 2002-06-04 Cisco Technology, Inc. Method and system for minimizing the connection set up time in high speed packet switching networks
US5889868A (en) 1996-07-02 1999-03-30 The Dice Company Optimization methods for the insertion, protection, and detection of digital watermarks in digitized data
US7095874B2 (en) 1996-07-02 2006-08-22 Wistaria Trading, Inc. Optimization methods for the insertion, protection, and detection of digital watermarks in digitized data
US7159116B2 (en) 1999-12-07 2007-01-02 Blue Spike, Inc. Systems, methods and devices for trusted transactions
US7346472B1 (en) 2000-09-07 2008-03-18 Blue Spike, Inc. Method and device for monitoring and analyzing signals
US7177429B2 (en) 2000-12-07 2007-02-13 Blue Spike, Inc. System and methods for permitting open access to data objects and for securing data within the data objects
US7457962B2 (en) 1996-07-02 2008-11-25 Wistaria Trading, Inc Optimization methods for the insertion, protection, and detection of digital watermarks in digitized data
US7730317B2 (en) * 1996-12-20 2010-06-01 Wistaria Trading, Inc. Linear predictive coding implementation of digital watermarks
US6934249B1 (en) 1997-04-01 2005-08-23 Cisco Technology, Inc. Method and system for minimizing the connection set up time in high speed packet switching networks
US6647028B1 (en) 1997-09-30 2003-11-11 Cisco Technology, Inc. System and method for recovering and restoring lost data in a N-channel coherent data transmission system
US6647008B1 (en) 1997-12-19 2003-11-11 Ibm Corporation Method and system for sharing reserved bandwidth between several dependent connections in high speed packet switching networks
US7177323B2 (en) * 1998-03-13 2007-02-13 Intel Corporation Ensuring quality of service (QOS) for a multi-media calls through call associated individual media stream bandwidth control
JP3134842B2 (ja) * 1998-05-08 2001-02-13 日本電気株式会社 マルチアクセス通信方式
EP1119952A1 (de) * 1998-10-05 2001-08-01 Lightel Systems Corporation Vorrichtung, verfahren und system zur implenentierung von netzwerken mit einer dienst qualität von null verzögerung mittels dichten wellenlängen multiplex
US7664264B2 (en) 1999-03-24 2010-02-16 Blue Spike, Inc. Utilizing data reduction in steganographic and cryptographic systems
US7475246B1 (en) 1999-08-04 2009-01-06 Blue Spike, Inc. Secure personal content server
US20030037170A1 (en) * 1999-08-13 2003-02-20 Markus Zeller House communication network
US6810422B1 (en) 2000-01-14 2004-10-26 Lockheed Martin Tactical Defense Systems System and method for probabilistic quality of communication service determination
US6671724B1 (en) 2000-03-21 2003-12-30 Centrisoft Corporation Software, systems and methods for managing a distributed network
US7260635B2 (en) * 2000-03-21 2007-08-21 Centrisoft Corporation Software, systems and methods for managing a distributed network
US7127615B2 (en) 2000-09-20 2006-10-24 Blue Spike, Inc. Security based on subliminal and supraliminal channels for data objects
US6854013B2 (en) * 2001-06-25 2005-02-08 Nortel Networks Limited Method and apparatus for optimizing network service
US7287275B2 (en) 2002-04-17 2007-10-23 Moskowitz Scott A Methods, systems and devices for packet watermarking and efficient provisioning of bandwidth
US8589499B2 (en) * 2002-05-10 2013-11-19 Silicon Graphics International Corp. Real-time storage area network
US10469341B2 (en) * 2017-10-26 2019-11-05 Microsoft Technology Licensing, Llc Intelligent connection management for multiple interfaces

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5136581A (en) * 1990-07-02 1992-08-04 At&T Bell Laboratories Arrangement for reserving and allocating a plurality of competing demands for an ordered bus communication network
DE69330371T2 (de) * 1993-04-19 2002-05-02 Ibm System zur netzwerkweiten Bandbreitenzuordnung
US5461611A (en) * 1994-06-07 1995-10-24 International Business Machines Corporation Quality of service management for source routing multimedia packet networks

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
H. TOKUDA ET AL.: "Continuous Media Communication with Dynamic QOS Control Using ARTS with an FDDI Network", COMPUTER COMMUNICATIONS REVIEW, vol. 22, no. 4, October 1992 (1992-10-01), NEW YORK US, pages 88 - 98, XP000371836 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2381996A (en) * 2001-10-30 2003-05-14 Hewlett Packard Co Network bandwidth optimization method and system
GB2381996B (en) * 2001-10-30 2004-10-06 Hewlett Packard Co Network bandwidth optimization method and system

Also Published As

Publication number Publication date
US5548579A (en) 1996-08-20

Similar Documents

Publication Publication Date Title
US5548579A (en) System for effective allocation of network-wide bandwidth
EP0621704B1 (de) System zur netzwerkweiten Bandbreitenzuordnung
US6820150B1 (en) Method and apparatus for providing quality-of-service delivery facilities over a bus
US5289461A (en) Interconnection method for digital multimedia communications
US6092113A (en) Method for constructing a VPN having an assured bandwidth
US5553073A (en) Token ring network
JPH09231143A (ja) 通信制御方法
JP5107339B2 (ja) アクティブ地理的冗長性のためのシステムおよび方法
US7746843B2 (en) Method of providing reliable transmission quality of service in a communication network
KR20020082213A (ko) 하이퍼랜 2 기술에 기초한 네트워크에서 등시성 자원을관리하기 위한 방법
US7305002B1 (en) Methods for controlling resources in a communication network
EP1263172A2 (de) Verfahren für das Handhaben der Betriebsmittel einer Verbindung in einem Kommunikationsnetz
CN108512779B (zh) 控制信息传递方法、服务器和系统
US5390182A (en) System for synchronous bandwidth allocation in token ring networks
WO2003045010A2 (en) Method and device for managing a connection and resource reservation in a communication network comprising a bridge
US5651007A (en) System of high availability synchronous bandwidth allocation over FDDI
JP2002118570A (ja) パケット通信方法および装置
JP2001036581A (ja) 通信帯域設定システムと方法
US6836802B1 (en) Network management system uses proxy agent for communicating control information and event notifications between network management apparatus and agents not directly connected to a network
JPH03101440A (ja) 帯域割当て方式
JP3555514B2 (ja) 品質保証型ネットワークシステム及び品質保証型通信方法
KR100385468B1 (ko) 비동기전달모드 교환기의 전용선 자원 공유방법
EP1800442B1 (de) Belastbarkeitslösung für bandbreitenverwalter auf oberster stufe
Cotroneo et al. A service differentiation scheme for the end-system
JP2002033762A (ja) ネットワークシステム

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AT BE DE DK ES FR GB IT NL SE

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 19960628